CAD4TB has been developed by Delft Imaging Systems in cooperation with the Radboud University Nijmegen and the Lung Institute in Cape Town. The involvement of academic researchers from the beginning demonstrates the intention to deliver a high-quality and reliable product. The publications have been divided into categories: the validation of CAD4TB, the technical aspects, field research, CAD4TB as a triage tool, reviews, and publications of the World Health Organisation (WHO) where CAD4TB was mentioned. You can read and download the paper by clicking on the title.
Technical aspects
- CAD4TB in chest X-rays using a combination of textural, focal, and shape abnormality analyis.
- An automated method to detect, segment, and remove foreign objects from chest radiographs.
- Fusion of local and global detection systems to detect TB in chest radiographs.
- Rib suppression in chest radiographs to improve classification of textual abnormalities.
- Segmentation of anatomical structures in chest radiographs
- Suppression of translucent elongated structures
- A method for automatic cavity segmentation in chest radiographs.
- Automatic detection of pleural effusion in chest radiographs.
- Improved texture analysis for automatic detection of TB with bone suppression images.
- Automated localization of costophrenic recesses and costophrenic angle measurement on frontal chest radiographs.
Field research